OCRRouter

DeepSeek-OCR vs Nougat

Pick DeepSeek-OCR for self-hosted bulk OCR in a commercial product, since its code and weights are MIT licensed. Pick Nougat for English arXiv-style papers where you need LaTeX math, but only for non-commercial work, because its weights are CC-BY-NC.

DeepSeek-OCRdeepseek/deepseek-ocrNougatmeta/nougat
TypeOpen sourceOpen source
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.1 s / page3.0 s / page
Best forCheap bulk conversionarXiv-style papers
InputsPDF, imagesPDF, images
Languages100+ languagesMainly English
Max pages per request200200
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
On OCRRouterAvailableAvailable

Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.

Which to choose

Choose DeepSeek-OCR if

  • The MIT license allows commercial use.
  • You can trade accuracy for cost with resolution modes from 64 to 400 vision tokens per page.
  • The authors quote about 2,500 tokens per second of PDF throughput on one A100-40G.

Choose Nougat if

  • It was trained on arXiv and PubMed Central documents, so it is built for academic papers.
  • It outputs LaTeX for equations and tables in Mathpix-compatible.mmd Markdown.
  • It ships small and base checkpoints with a simple CLI and API.

Key differences

DeepSeek-OCRNougat
LicenceMITCode MIT; weights CC-BY-NC, so no commercial use
PricingFree, self-hosted (you pay for compute)Free for non-commercial use, self-hosted (you pay for compute)
Output formatsMarkdown, plain text, HTML, bounding boxesMarkdown and LaTeX
Target documentsGeneral pages; good for cheap bulk OCREnglish scientific papers and math-heavy PDFs; not for business documents, forms or invoices
LanguagesNot publishedWorks best on English; the README says Chinese, Russian and Japanese do not work
HardwareCUDA GPU; reference setup CUDA 11.8 and PyTorch 2.6 in bfloat16Self-hosted Python package; the repeat-detection threshold is tuned to one GPU type (issue #11)
Known failureRepeated tokens and looping over table headers (issues #12 and #16); it corrects nonsense words instead of copying themRepetition loops on 1.5% of test pages, more on out-of-domain documents; looping pages can be dropped as MISSING_PAGE

Sources

What each one is

DeepSeek-OCR

Open-source vision model that compresses pages into few tokens.

DeepSeek-OCR details

Nougat

Meta's model that converts academic PDFs to Markdown with LaTeX math.

Nougat details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

Use one, fall back to the other

{"model": "deepseek/deepseek-ocr","fallbacks": ["meta/nougat"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

DeepSeek-OCR alternativesNougat alternativesBest OCR models in 2026